© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 5798
    Prev
    Next
    INDEX
    Explanations

    phrases indicating consistency or agreement with previous research findings

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.70
    abestanden
    -0.63
    +#+
    -0.58
     tố
    -0.55
    жели
    -0.55
     OnInit
    -0.52
    DotNetBar
    -0.52
    verwijspagina
    -0.52
    URLException
    -0.51
    AutoScale
    -0.47
    POSITIVE LOGITS
    دانشنامهٔ
    0.65
    预期
    0.60
     légende
    0.57
    MethodManager
    0.57
     jPanel
    0.56
    niosek
    0.56
     expected
    0.54
    expected
    0.53
    });*/
    0.53
    []);
    0.53
    Activations Density 0.251%

    No Known Activations